Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and functionalities related to software and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Automatic actions or behaviors

    np_acts-logits-general · gemini-2.0-flash

    automatically or automatic actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    marginHorizontal
    -0.68
    MarshalTo
    -0.47
     muzzle
    -0.44
    rawDesc
    -0.43
    UnitTesting
    -0.43
     dekat
    -0.42
    übt
    -0.42
     داشتم
    -0.41
     experimenter
    -0.41
     tritt
    -0.41
    POSITIVE LOGITS
     automatically
    1.58
    automatically
    1.28
     automatic
    1.27
     Automatically
    1.25
     automatiquement
    1.15
     AUTOMATIC
    1.14
     automaticamente
    1.11
     automatisch
    1.09
    Automatically
    1.08
     detect
    1.07
    Act Density 0.764%

    No Known Activations